Abstract
The deep convolutional neural network (CNN) has recently become the prevailing framework for person search. Nevertheless, these approaches suffer from the high computational cost, raising the necessity of compressing deep models for applicability on resource-restrained platforms. Despite of the promising performance achieved in boosting efficiency for general vision tasks, current model compression methods are not specifically designed for person search, thus leaving much room for improvement. In this paper, we make the first attempt in investigating model pruning for person search, and propose a novel loss-based channel pruning approach, namely Sub-task Aware Model Pruning with Layer-wise Channel Balancing (SAMP). It firstly develops a Sub-task aware Channel Importance (SaCI) estimation to deal with the inconsistent sub-tasks, i.e. person detection and re-identification, of person search. Subsequently, a Layer-wise Channel Balancing (LCB) mechanism is employed to progressively assign a minimal number of channels to be preserved for each layer, thus avoiding over-pruning. Finally, an Adaptive OIM (AdaOIM) loss is presented for pruning and post-training via dynamically refining the degraded class-wise prototype features by leveraging the ones from the full model. Experiments on CUHK-SYSU and PRW demonstrate the effectiveness of our method, by comparing with the state-of-the-art channel pruning approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chang, X., Li, Y., Oymak, S., et al.: Provable benefits of overparameterization in model compression: from double descent to pruning neural networks. In: AAAI Conference on Artificial Intelligence, pp. 6974–6983 (2021)
Chen, K., Wang, J., Pang, J., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)
Deng, L., Li, G., Han, S., et al.: Model compression and hardware acceleration for neural networks: a comprehensive survey. Proc. IEEE 108(4), 485–532 (2020)
Doering, A., Chen, D., Zhang, S., et al.: PoseTrack21: a dataset for person search, multi-object tracking and multi-person pose tracking. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20963–20972 (2022)
Fang, G., Ma, X., Song, M., et al.: Depgraph: towards any structural pruning. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16091–16101 (2023)
Feng, D., Yang, J., Wei, Y., et al.: An efficient person search method using spatio-temporal features for surveillance videos. Appl. Sci. 12(15), 7670 (2022)
Gao, C., Cai, G., Jiang, X., et al.: Conditional feature learning based transformer for text-based person search. IEEE Trans. Image Process. 31, 6097–6108 (2022)
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and huffman coding. In: International Conference on Learning Representations (2016)
Han, S., Pool, J., Tran, J., et al.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, pp. 1135–1143 (2015)
Howard, A.G., Zhu, M., Chen, B., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Hu, H., Peng, R., Tai, Y.W., et al.: Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250 (2016)
Jaffe, L., Zakhor, A.: Gallery filter network for person search. In: IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1684–1693 (2023)
Li, J., Liang, F., Li, Y., et al.: Fast person search pipeline. In: IEEE International Conference on Multimedia and Expo, pp. 1114–1119 (2019)
Li, J., Yan, Y., Wang, G., et al.: Domain adaptive person search. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13674, pp. 302–318. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19781-9_18
Li, Z., Miao, D.: Sequential end-to-end network for efficient person search. In: AAAI Conference on Artificial Intelligence, pp. 2011–2019 (2021)
Lin, X., Ren, P., Xiao, Y., et al.: Person search challenges and solutions: a survey. In: International Joint Conference on Artificial Intelligence, pp. 4500–4507 (2021)
Liu, J., Zhuang, B., Zhuang, Z., et al.: Discrimination-aware network pruning for deep model compression. IEEE Trans. Pattern Anal. Mach. Intell. 44(8), 4035–4051 (2021)
Liu, L., Zhang, S., Kuang, Z., et al.: Group fisher pruning for practical network compression. In: International Conference on Machine Learning, pp. 7021–7032 (2021)
Meng, F., Cheng, H., Li, K., et al.: Pruning filter in filter. In: Advances in Neural Information Processing Systems, pp. 17629–17640 (2020)
Mirzadeh, S.I., Farajtabar, M., Li, A., et al.: Improved knowledge distillation via teacher assistant. In: AAAI Conference on Artificial Intelligence, pp. 5191–5198 (2020)
Russakovsky, O., Deng, J., Su, H., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211–252 (2015)
Wang, H., Qin, C., Zhang, Y., et al.: Neural pruning via growing regularization. In: International Conference on Learning Representations (2021)
Xiao, T., Li, S., Wang, B., et al.: End-to-end deep learning for person search. arXiv preprint arXiv:1604.01850 (2016)
Xiao, T., Li, S., Wang, B., et al.: Joint detection and identification feature learning for person search. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3415–3424 (2017)
Xie, H., Jiang, W., Luo, H., et al.: Model compression via pruning and knowledge distillation for person re-identification. J. Ambient. Intell. Humaniz. Comput. 12, 2149–2161 (2021)
Xu, Y., Ma, B., Huang, R., et al.: Person search in a scene by jointly modeling people commonness and person uniqueness. In: ACM International Conference on Multimedia, pp. 937–940 (2014)
Yan, Y., Li, J., Qin, J., et al.: Anchor-free person search. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7690–7699 (2021)
Yeom, S.K., Seegerer, P., Lapuschkin, S., et al.: Pruning by explaining: a novel criterion for deep neural network pruning. Pattern Recogn. 115, 107899 (2021)
Yu, J., Yang, L., Xu, N., et al.: Slimmable neural networks. In: International Conference on Learning Representations (2018)
Yu, X., Liu, T., Wang, X., et al.: On compressing deep models by low rank and sparse decomposition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7370–7379 (2017)
Zheng, L., Shen, L., Tian, L., et al.: Scalable person re-identification: a benchmark. In: IEEE International Conference on Computer Vision, pp. 1116–1124 (2015)
Zheng, L., Zhang, H., Sun, S., et al.: Person re-identification in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1367–1376 (2017)
Zheng, Y.J., Chen, S.B., Ding, C.H., et al.: Model compression based on differentiable network channel pruning. IEEE Trans. Neural Netw. Learn. Syst. (2022)
Acknowledgements
This work is supported by the National Key R &D Program of China (2021ZD0110503), the National Natural Science Foundation of China (62202034), the Research Program of State Key Laboratory of Virtual Reality Technology and Systems, and the grant No. KZ46009501.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wu, Z., Chen, J., Wang, Y. (2024). SAMP: Sub-task Aware Model Pruning with Layer-Wise Channel Balancing for Person Search. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14434. Springer, Singapore. https://doi.org/10.1007/978-981-99-8549-4_17
Download citation
DOI: https://doi.org/10.1007/978-981-99-8549-4_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8548-7
Online ISBN: 978-981-99-8549-4
eBook Packages: Computer ScienceComputer Science (R0)